Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 11
    Prev
    Next
    INDEX
    Explanations

    scientific terms related to measurement and normalization in experiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EconPapers
    -0.69
     GenerationType
    -0.68
     nakalista
    -0.63
    tvguidetime
    -0.61
     EdgeInsets
    -0.59
     թվական
    -0.59
    SOUNDBITE
    -0.59
     препратки
    -0.58
    CppCodeGen
    -0.57
    detectChanges
    -0.57
    POSITIVE LOGITS
    webElementXpaths
    0.57
     القديمة
    0.47
     الاطلاع
    0.47
    contentLoaded
    0.46
     knows
    0.46
    XtraReports
    0.44
    fera
    0.44
    dehyde
    0.43
    ities
    0.42
     gained
    0.42
    Activations Density 1.426%

    No Known Activations